Skin tone filter

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media for receiving a set of images at a social media system, wherein each image includes one or more recognized features associated with one or more lightness values; indexing each image using the one or more recognized features and the associated range of lightness values; receiving a query; determining a first group of images that is responsive to the query; determining that the query triggers a lightness filter to be displayed on the user device; providing the first group of images for display on a user interface with one or more lightness filter indicators; and in response to a user selection of one of the one or more lightness filter indicators: filtering the first group of images to determine a filtered group of images, and updating the images provided for display according to the filtered group of images.

The invention claimed is: 
     
       1. A computer-implemented method comprising:
 determining, for each image of a collection of images, a respective lightness value; 
 associating the respective lightness value for each corresponding image of the collection of images; 
 determining, in response to a query, a first plurality of images from the collection of images that are responsive to the query; 
 causing the first plurality of images to be presented on a client device; 
 causing a lightness filter including a plurality of lightness filter indicators to be presented on the client device; 
 receiving a first interaction with a first lightness filter indictor of the plurality of lightness filter indicators indicating a selection of the first lightness filter indicator; 
 determining, based at least in part on the selection with the first lightness filter indicator, a second plurality of images from the first plurality of images; and 
 causing the second plurality of images to be presented on the client device. 
 
     
     
       2. The computer-implemented method of  claim 1 , wherein each lightness filter indicator of the plurality of lightness filter indicators corresponds to a range of lightness values. 
     
     
       3. The computer-implemented method of  claim 1 , wherein determining the second plurality of images from the first plurality of images includes determining that the respective lightness values associated with the second plurality of images is within a range of lightness values associated with the first lightness filter indicator. 
     
     
       4. The computer-implemented method of  claim 1 , wherein the respective lightness values correspond to at least one of a CIELAB color space or a RGB color space. 
     
     
       5. The computer-implemented method of  claim 1 , wherein each respective lightness value corresponds to at least one of a skin tone associated with a body part of a first subject or a hair of a second subject. 
     
     
       6. A computing system, comprising:
 one or more processors; and 
 a memory including program instructions that, when executed by the one or more processors, cause the one or more processors to at least:
 determine, in response to a query, a first plurality of images from a collection of images that are responsive to the query, wherein at least a portion of the first plurality of images includes an associated skin tone value; 
 cause at least a portion of the first plurality of images to be presented on a client device; 
 determine, based at least in part on a first selection of a first skin tone filter indicator, a second plurality of images from the first plurality of images; and 
 cause at least a portion of the second plurality of images to be presented on the client device. 
 
 
     
     
       7. The computing system of  claim 6 , wherein:
 the program instructions that, when executed by the one or more processors, further cause the one or more processors to at least:
 determine that the query triggers skin tone filtering; and 
 cause a skin tone filter that includes a plurality of skin tone filter indicators to be presented concurrently with the at least a portion of the first plurality of images; and 
 
 the first skin tone filter indicator is selected from the plurality of skin tone filter indicators. 
 
     
     
       8. The computing system of  claim 7 , wherein each skin tone filter indicator of the plurality of skin tone filter indicators corresponds to a range of skin tone values. 
     
     
       9. The computing system of  claim 7 , wherein determining that the query triggers skin tone filtering includes:
 determining that at least one query term of the query is included in a predetermined plurality of keywords. 
 
     
     
       10. The computing system of  claim 6 , wherein determining the second plurality of images from the first plurality of images includes determining that the associated skin tone values of the second plurality of images is within a range of skin tone values associated with the skin tone filter indicator. 
     
     
       11. The computing system of  claim 6 , wherein the program instructions that, when executed by the one or more processors, further cause the one or more processors to at least:
 determine, for each image of the collection of images, a respective lightness value; and 
 associate the respective lightness value for each corresponding image of the collection of images. 
 
     
     
       12. The computing system of  claim 11 , wherein determining the respective lightness values for each image of the collection of images includes:
 determining at least one feature lightness value corresponding to at least one body portion represented in each image. 
 
     
     
       13. The computing system of  claim 12 , wherein:
 the at least one feature lightness value includes a plurality of feature lightness values; and 
 determining respective lightness values includes an average lightness value that is based at least in part on a combination of the plurality of feature lightness values. 
 
     
     
       14. The computing system of  claim 6 , wherein the program instructions that, when executed by the one or more processors, further cause the one or more processors to at least:
 determine, based at least in part on a second selection of a second skin tone filter indicator, a third plurality of images from the first plurality of images; and 
 cause at least a portion of the third plurality of images and at least a portion of the second plurality of images to be presented on the client device. 
 
     
     
       15. The computing system of  claim 6 , wherein the program instructions that, when executed by the one or more processors, further cause the one or more processors to at least:
 rewrite the query based at least in part on the first selection of the skin tone filter indicator to generate a rewritten query; 
 determine, based at least in part on the rewritten query, a third plurality of images from the collection of images that are responsive to the rewritten query; and 
 cause at least a portion of the third plurality of images to be presented on the client device. 
 
     
     
       16. A method, comprising:
 determining, in response to a query, a first plurality of images that are responsive to the query, wherein at least a portion of the first plurality of images includes an associated skin tone value; 
 causing at least a portion of the first plurality of images to be presented on a client device; 
 causing a skin tone filter including a plurality of user-selectable skin tone filter indicators to be presented on the client device concurrently with the presentation of the at least a portion of the first plurality of images; 
 determining, based at least in part on a first selection of a first skin tone filter indicator, a second plurality of images from the first plurality of images; and 
 causing at least a portion of the second portion of images to be presented on the client device. 
 
     
     
       17. The method of  claim 16 , further comprising:
 determining that the query triggers skin tone filtering, 
 wherein causing the skin tone filter to be presented on the client device is in response to the determination that the query triggers skin tone filtering. 
 
     
     
       18. The method of  claim 17 , wherein determining that the query triggers skin tone filtering includes:
 determining that at least one query term of the query is included in a predetermined plurality of keywords. 
 
     
     
       19. The method of  claim 16 , further comprising:
 determining, based at least in part on a second selection of a second skin tone filter indicator, a third plurality of images from the first plurality of images; and 
 causing at least a portion of the third plurality of images and at least a portion of the second plurality of images to be presented on the client device. 
 
     
     
       20. The method of  claim 16 , further comprising:
 rewriting the query based at least in part on the first selection of the skin tone filter indicator to generate a rewritten query; 
 determining, based at least in part on the rewritten query, a third plurality of images from a collection of images that are responsive to the rewritten query; and 
 causing at least a portion of the third plurality of images to be presented on the client device.